AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval

Yulong Hui, Chao Chen, Zhihang Fu, Yihao Liu, Jieping Ye, Huanchen Zhang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
give the agent interaction primitives instead of black-box semantic search (ablation)Interact-RAG · 2Wiki / MuSiQue / PopQAEM: 63.4 -> 69.6 (2Wiki), 30.1 -> 34.8 (MuSiQue), 50.2 -> 56.0 (PopQA)Improved
add SFT on synthesized trajectories before RL (ablation)Interact-RAG · 2Wiki / MuSiQue / PopQAEM: 59.0 -> 69.6 (2Wiki), 26.4 -> 34.8 (MuSiQue), 52.2 -> 56.0 (PopQA)Improved
add RL (GRPO) after SFT (ablation)Interact-RAG · 2Wiki / MuSiQue / PopQAEM: 65.2 -> 69.6 (2Wiki), 28.1 -> 34.8 (MuSiQue), 45.6 -> 56.0 (PopQA)Improved
add Multi-faceted Retrieval primitives (ablation)Interact-RAG · 2Wiki / MuSiQue / PopQAEM: 66.0 -> 69.6 (2Wiki), 34.6 -> 34.8 (MuSiQue)Improved
add Anchored Matching primitive (ablation)Interact-RAG · 2Wiki / PopQAEM: 66.3 -> 69.6 (2Wiki), 53.4 -> 56.0 (PopQA)Improved
add Context Shaping primitives (ablation)Interact-RAG · MuSiQueEM: 33.6 -> 34.8Improved
add the reasoning-enhanced workflow (planner, reasoner, executor) over a single prompt (ablation)Interact-RAG-Workflow (training-free) · 2Wiki / MuSiQue / PopQAEM: 52.0 -> 60.1 (2Wiki), 21.8 -> 24.1 (MuSiQue), 40.0 -> 43.6 (PopQA)Improved
add interaction primitives to the training-free workflow (ablation)Interact-RAG-Workflow · 2Wiki / MuSiQue / PopQAEM: 56.3 -> 60.1 (2Wiki), 18.8 -> 24.1 (MuSiQue), 38.7 -> 43.6 (PopQA)Improved
use SFT then RL rather than RL only (ablation)Interact-RAG training · sampled subset of six test setsEMImproved
replace agent-weighted fusion with RRF or CombMNZ (ablation)Multi-faceted retrieval · 2Wiki / MuSiQue / PopQAEM: RRF 68.7, CombMNZ 69.8 vs 69.6 on 2WikiNo clear effect
apply Best-of-3 sampling to Search-R1 instead of Interact-RAGSearch-R1 · 2WikiMultiHopQAEM: 50.9 -> 56.2Improved
use Interact-RAG instead of Search-R1 for inference costInteract-RAG-7B · 2WikiMultiHopQAlatency (s): 17.2 -> 36.4Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy